NVIDIA GeForce RTX 5090 Mobile vs NVIDIA Quadro GV100 Comparison

FAQ

Q: How does the NVIDIA GeForce RTX 5090 Mobile compare to the Quadro GV100 in overall benchmark score?

A: The RTX 5090 Mobile has an average benchmark score of 45152, which is 27.1% higher than the Quadro GV100's 35520. The RTX 5090 Mobile also sits at the 84th percentile of all GPUs, compared to the GV100's 80th percentile.

Q: Which GPU wins the most benchmark tests?

A: The RTX 5090 Mobile wins all nine head-to-head benchmark comparisons. The largest margin is in Passmark DirectX 12, where it leads by 64.3%, and the smallest margin is in Passmark G2D, where it leads by 26.4%.

Q: What are the memory differences between these two cards?

A: The Quadro GV100 has more memory at 32 GB of HBM2 with a 4096-bit bus, while the RTX 5090 Mobile has 24 GB of GDDR7 with a 256-bit bus. The RTX 5090 Mobile has slightly higher memory bandwidth at 896.0 GB/s versus 868.4 GB/s.

Q: Which GPU has the higher transistor count?

A: The RTX 5090 Mobile has 45,600 million transistors on a 5 nm process, while the Quadro GV100 has 21,100 million transistors on a 12 nm process. However, the GV100 has a larger die size at 815 mm² compared to 378 mm².

Q: What is the release date and production status of each?

A: The RTX 5090 Mobile was released on March 26, 2025, and is active in production. The Quadro GV100 was also released on March 26, but in 2018, and is now end-of-life.

Q: How do their compute scores compare?

A: In Passmark GPU Compute, the RTX 5090 Mobile scores 13401 versus 9069 for the GV100, a 47.8% advantage. In Geekbench OpenCL, the RTX 5090 Mobile scores 201834 versus 150004, a 34.6% advantage.

Architecture Differences

The two GPUs represent entirely different architectural generations from NVIDIA. The RTX 5090 Mobile is built on the Blackwell 2.0 architecture using the GB203 chip, fabricated on a 5 nm process at TSMC. The Quadro GV100 uses the older Volta architecture with the GV100 chip, manufactured on a 12 nm process, also at TSMC. This process gap is substantial: the RTX 5090 Mobile achieves a transistor density of 120.6 million transistors per square millimeter, while the GV100 manages only 25.9 million per square millimeter.

The transistor counts reflect this difference. The RTX 5090 Mobile packs 45,600 million transistors into a 378 mm² die, while the GV100 contains 21,100 million transistors across an 815 mm² die. Despite having fewer total transistors, the GV100's larger die means it requires a dual-slot cooling and a 250 W TDP, whereas the RTX 5090 Mobile is an IGP-class chip with a 95 W TDP and no power connectors.

Feature support diverges sharply. The RTX 5090 Mobile includes dedicated ray tracing cores (82 RT cores total, a capability the GV100 lacks entirely) and 328 tensor cores used for AI workloads. The GV100 also features 640 tensor cores, which is actually more than the RTX 5090 Mobile's 328, but has no RT cores at all. The RTX 5090 Mobile uses GDDR7 memory with 1750 MHz (28 Gbps effective clock, while the GV100 relies on HBM2 at 848 MHz (1696 Mbps effective). Both cards support DirectX 12, but the RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), which is a higher specification than the GV100's DirectX 12 (12_1).

The RTX 5090 Mobile also benefits from a PCIe 5.0 x16 interface, while the GV100 uses PCIe 3.0 x16. The GV100 offers four DisplayPort 1.4a outputs, whereas the RTX 5090 Mobile's display outputs are portable device dependent. The GV100 measures 267 mm (10.5 inches) in length and 111 mm (4.4 inches) in height, while the RTX 5090 Mobile has no listed dimensions.

The RTX 5090 Mobile's predecessor is the GeForce 40 Mobile series, and the GV100's predecessor is Quadro Pascal, with its successor being Quadro Turing.

Where Each One Wins

The RTX 5090 Mobile wins every benchmark category in the head-to-head comparison, meaning there is no test in the recorded data where the Quadro GV100 takes a victory. However, the magnitude of the RTX 5090 Mobile's advantage varies by workload type, which reveals where each GPU is relatively stronger.

The RTX 5090 Mobile's largest win is in DirectX 64.3% advantage in Passmark DirectX 12, which points to a significant lead in modern, DirectX 12-specific rendering workloads. Its next biggest win is 60.1% in Passmark DirectX 11, and 56.5% in Passmark DirectX 9. These results indicate a comprehensive lead across API generations. The RTX 5090 Mobile is also strong in compute workloads, with a 47.8% lead in Passmark GPU Compute and 42.2% in Geekbench Vulkan.

The Quadro GV100 is at its closest in the DirectX 10 test, losing by a smaller 30.7%, and in Passmark G2D (2D graphics throughput, 26.4% behind). The GV100 draws nearest in Geekbench OpenCL with a 34.4% gap, its smallest compute deficit. The GV100's tensor core count (640) may keep it competitive in certain compute tasks, but the data does not show any test where it overcomes the RTX 5090 Mobile.

For users with the GV100, the GV100's strengths are its larger memory capacity (32 GB versus 24 GB) and higher pixel rate (208.3 GPixel/s versus 169.7 GPixel/s). It also has a higher boost clock at 1627 MHz versus 1515 MHz. These advantages, however, do not translate into any benchmark win in the recorded data.

Specification Differences

The specifications reveal two very different power profiles. The RTX 990 MHz base clock and 1515 MHz boost clock, which are lower than the GV100's 1132 MHz base and 1627 MHz boost. Despite lower clocks, the RTX 5090 Mobile achieves higher FP32 performance at 31.80 TFLOPS versus 16.66 TFLOPS. In FP16, the RTX 5090 Mobile delivers 31.80 TFLOPS at a 1:1 ratio, while the GV100 reaches 33.32 TFLOPS at a 2:1 ratio.

The RTX 5090 Mobile has 10496 shading units, 328 TMUs, and 112 ROPs. The GV100 has 5120 shading units, 320 TMUs, and 128 ROPs. The RTX 5090 Mobile has 82 RT cores and 328 tensor cores; the GV100 has no RT cores, but 640 tensor cores. Pixel rates favor the GV100 at 208.3 GPixel/s versus 169.7 GPixel/s, while texture rate favors the RTX 5090 Mobile at 496.9 GTexel/s versus 520.6 GTexel/s, a smaller gap.

Memory configurations are a key differentiator. The RTX 5090 Mobile has 24 GB GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth. The GV100 has 32 GB HBM2 on a 4096-bit bus with 868.4 GB/s. The RTX 5090 Mobile's memory clock is 1750 MHz (28 Gbps effective), while the GV100's is 848 MHz (1696 Mbps effective). Power also differs: the RTX 5090 Mobile is a 95 W IGP with no power connectors, while the GV100 is a 250 W dual-slot card requiring one 8-pin connector and a 600 W suggested power supply. The GV100 has a launch MSRP of 8,999 USD, which was its launch price (the RTX 5090 Mobile has no listed launch MSRP). The GV100 is end-of-life, while the RTX 5090 Mobile is active.

Head-to-Head Benchmarks

The RTX 5090 Mobile's most decisive victory is Passmark DirectX 12, where it scores 138 versus 84, a 64.3% lead. This is the single largest margin in the comparison. Passmark DirectX 11 follows with 269 versus 168, a 60.1% advantage. Passmark DirectX 9 shows 324 versus 207, a 56.5% victory, and Passmark G3D yields 30034 versus 19650, a 52.8% lead.

Compute workloads also show a strong lead for the RTX 5090 Mobile. Passmark GPU Compute scores 13401 versus 9069, a 47.8% difference. Geekbench Vulkan shows 198405 versus 139526, a 42.2% advantage. Geekbench OpenCL scores 201834 versus 150004, a 34.6% lead. Even the closest tests, Passmark DirectX 10 (183 versus 140, 30.7% lead) and Passmark G2D (1057 versus 836, 26.4% lead), favor the RTX 5090 Mobile. Across all nine tests, the RTX 5090 Mobile wins every single matchup.

The RTX 5090 Mobile's nearest rivals, based on average benchmark score, include the AMD Radeon Pro 5500 XT at 45384 (-0.5%), NVIDIA GeForce RTX 4070 Ti at 44795 (0.8%), Intel Arc A730M at 45592 (-1%), and NVIDIA RTX 5880 Ada Generation at 45972 (-1.8%). The GV100's nearest rivals include the NVIDIA GeForce RTX 5070 Ti Mobile at 35435 (0.2%), AMD Radeon Pro Duo at 35860 (-0.9%), NVIDIA T1000 at 36289 (-2.1%), and NVIDIA A2 at 34690 (2.4%). The GV100's 35520 average places it just above the RTX 5070 Ti Mobile, while the RTX 5090 Mobile's 45152 average places it between the RTX 4070 Ti and under the Arc A730M.

The Verdict

The data is unambiguous on the RTX 5090 Mobile. It wins all nine head-to-head tests, leads by a minimum of 26.4% in any individual test, and holds a 27.1% overall average score advantage over the Quadro GV100. It has a higher transistor density, a 5 nm process, and support for modern features like RT cores. The RTX 5090 Mobile is the more capable GPU for any user seeking peak performance in DirectX 12, DirectX 11, DirectX 9, Vulkan, OpenCL, G3D, G2D, or compute workloads.

The Quadro GV100, for users in the database, is a Volta-generation product with 32 GB of HBM2 memory, a 4096-bit bus, and a higher boost clock at 1627 MHz. It has more tensor cores (640), a higher pixel rate, and a larger die. It is also end-of-life and was released in 2018. Its only advantages are memory capacity, pixel rate, and tensor core count, none of which translate into a single benchmark win.

For users considering these two options, the RTX The RTX 5090 Mobile is the choice for anyone who wants better performance across every recorded benchmark, and the GV100 is also outmatched by the RTX 5090 Mobile by 27.1%. The RTX 5090 Mobile also has a lower TDP of 95 W and a PCIe 5.0 x16 interface, while the GV100 requires 250 W and PCIe 3.0 x16. The RTX 5090 Mobile's 1515 MHz boost clock is lower than the GV100's 1627 MHz boost, but the RTX 5090 Mobile still achieves higher FP32 TFLOPS and higher texture rate. The RTX 5090 Mobile is the recommended GPU from the data.